A portable and rapid gutter oil detector based on multi-feature neural network

Authors

ZHANG Zhi-peng, Department of Electronic and Computer Engineering, Southeast University Chengxian College, Nanjing, Jiangsu 210088, China
HUANG Shi-zhen, Fujian Key Lab of Microelectronics & Integrated Circuits, Fuzhou University, Fuzhou, Fujian 350116, China
LIN Meng-ru, Fujian Key Lab of Microelectronics & Integrated Circuits, Fuzhou University, Fuzhou, Fujian 350116, China
LU Qing-ru, Department of Electronic and Computer Engineering, Southeast University Chengxian College, Nanjing, Jiangsu 210088, China
LIN Yan, Department of Electronic and Computer Engineering, Southeast University Chengxian College, Nanjing, Jiangsu 210088, China; Fujian Key Lab of Microelectronics & Integrated Circuits, Fuzhou University, Fuzhou, Fujian 350116, China
CHEN Rui-qi, Fujian Key Lab of Microelectronics & Integrated Circuits, Fuzhou University, Fuzhou, Fujian 350116, China; Verimake Research, Nanjing Renmian IC-tech Co., Ltd., Nanjing, Jiangsu 210000, China

Abstract

An offline oil detection device is designed based on the heterogeneous architecture of a System on a Programmable Chip (SoPC). The SoPC platform is constructed by porting Cortex-M0 soft core to Field Programmable Gate Array (FPGA). Using FPGA hardware resources, the operation order is optimized through the pipeline design with serial-parallel hybrid methods. Moreover, the parameter calibration accelerator and neural network accelerator are designed and connected to the bus system. Experimental results show that this device can perform the qualitative analysis and classification of gutter oil accurately with high detection efficiency. Compared with the traditional similar terminal gutter oil detection equipment, the detection time is shortened by 89%. Moreover, the data processing speed of SoPC increases by twice comparing to Cortex-A9, with the introduction of accelerator.

Publication Date

5-28-2021

First Page

47

Last Page

52,232

DOI

10.13652/j.issn.1003-5788.2021.05.009

Recommended Citation

Zhi-peng, ZHANG; Shi-zhen, HUANG; Meng-ru, LIN; Qing-ru, LU; Yan, LIN; and Rui-qi, CHEN (2021) "A portable and rapid gutter oil detector based on multi-feature neural network," Food and Machinery: Vol. 37: Iss. 5, Article 9.
DOI: 10.13652/j.issn.1003-5788.2021.05.009
Available at: https://www.ifoodmm.cn/journal/vol37/iss5/9

References

[1] 王龙星, 金静, 王淑秋, 等. 非正常食用油鉴别新方法（一）: 3种辣椒碱残留量的液相色谱—质谱分析[J]. 色谱, 2012, 30（11）: 1 094-1 099.
[2] LIN Chu-pao, LIAO Chang-rui, ZHANG Yun-fang,et al. Optofluidic gutter oil discrimination based on a hybrid-waveguide coupler in fibre[J]. Lab on a Chip, 2018, 18 （4）: 595-600.
[3] HU Rui, HE Ting, ZHANG Zhao-wei, et al. Safety analysis of edible oil products via Raman spectroscopy[J]. Talanta, 2019, 191: 324-332.
[4] 李娟, 黄木花, 燕一波, 等. 植物油中掺煎炸动物油的近红外快速无损检测[J]. 食品与机械, 2020, 36（6）: 99-102.
[5] 杨扬, 殷乐, 尹芳华, 等. 几种食用油的核磁共振光谱特征与地沟油的快速检测[J]. 中国油脂, 2015, 40（7）: 45-50.
[6] 葛亮, 胡泽. 一种食用油掺杂地沟油快速检测系统的设计[J]. 中国油脂, 2014, 39（3）: 39-41.
[7] 罗世霞, 商明菊, 吕研, 等. 地沟油与食用油理化指标的对比分析[J]. 广州化工, 2014（17）: 97-98.
[8] 章丽燕, 周潮君. 地沟油检出方法的研究[J]. 龙岩学院学报, 2012（5）: 20-23.
[9] 刘丹, 王运宏. 限制型自适应SUSAN边缘检测算法[J]. 计算机辅助设计与图形学学报, 2020, 32（6）: 118-125.
[10] 李秋梅. 基于Cortex-M3的地沟油快速检测系统研究[J]. 自动化技术与应用, 2019, 38（4）: 131-133.
[11] 王凯. 气象传感器自动批量测试系统的设计[D]. 南京: 东南大学, 2016: 2.
[12] 赵鑫超, 吴振鹏, 王鹏, 等. 油脂样品过氧化值的测定与评价[J]. 科技创新与应用, 2018（4）: 7, 10.
[13] 胡雪瑶, 吴次南. 基于电导率的地沟油快速鉴别方法的改进[J]. 应用物理, 2013（8）: 162-165.
[14] 胡欣宇. 基于电导率法的地沟油含量测定[J]. 物联网技术, 2017（5）: 32-34, 37.
[15] KABIR S, ISLAM R U, HOSSAIN M S, et al. An integrated approach of belief rule base and deep learning to predict air pollution[J]. Sensors, 2020, 20 （7）: 1 956.
[16] LAVI B, SERJ M F, ULLAH I. Survey on deep learning techniques for person re-identification task[J]. arXiv e-prints, 2018, 13（7）: 1807.05284.
[17] ROUKHAMI M, LAZARESCU M T, GREGORETTI F, et al. Very low power neural network FPGA accelerators for tag-less remote person identification using capacitive sensors[J]. IEEE Access, 2019（7）: 102 217-102 231.
[18] 张国城. 酸度、电导、溶解氧分析仪温度补偿的区别与联系[J]. 分析仪器, 2019（4）: 44-47.
[19] 陈大科. 一种采用FPGA实现CORTEX-M0 IP核验证的方法[J]. 微电子学与计算机, 2018, 35（3）: 135-139.
[20] 何宾. ARM Cortex-M0全可编程SoC原理即实现:面向处理器、协议、外设、编程和操作系统[M]. 北京: 清华大学出版社, 2017: 157-160.
[21] EVANS A, URBINA ORTEGA C, MARINISK, et al. Heavy-ion micro beam and simulation study of a flash-based FPGA microcontroller implementation[J]. IEEE Transactions on Nuclear Science, 2017, 64（1）: 504-511.
[22] WANG Meng-zhu, HUYAN Zong-yao, JING Bing-yu, et al. Analysis of edible oil oxidation based on changes in the electrical conductivity of the extracted aqueous phase[J]. European Journal of Lipid Science and Technology, 2019, 121（5）: 1800441.
[23] OKAFOR A C, NWOGUH T O. A study of viscosity and thermal conductivity of vegetable oils as base cutting fluids for minimum quantity lubrication machining of difficult-to-cut metals[J]. The International Journal of Advanced Manufacturing Technology, 2020, 106（3/4）: 1 121-1 131.
[24] 陈奇, 何理旭, 陈贤龙, 等. 一种基于SVM的新型地沟油检测方法及检测装置: CN109871887A[P]. 2019-06-11.
[25] GE Fen, WU Ning, XIAO Hao, et al. Compact convolutional neural network accelerator for IoT endpoint SoC[J]. Electronics, 2019, 8（5）: 497-511.
[26] CROCIONI G, PAU D, DELORME J M, et al. Li-Ion batteries parameter estimation with tiny neural networks embedded on intelligent IoT microcontrollers[J]. IEEE Access, 2020, 8: 122 135-122 146.